faster-whisper-GUI model download https://huggingface.co/models?sort=trending&search=faster-whisper you can also download and convert models in software large-v3 model float32 : Huggingface 百度云网盘链接 What's this Best wishes to the world that received this message ...
升级faster-whisper 至 1.0.3 版本 Silero VAD V5 model 经过反复测试 Silero V5 模型在背景复杂的情况下表现不佳,请按需升级 提示 软件需要完全卸载旧版之后安装新版(cache文件夹可不做清理) 需要安装 ffmpeg 0.8.1 Changes Upgrade faster-whisper to version 1.0.3 Silero VAD V5 model After repeated ...
Faster-Whisperhttps://github.com/SYSTRAN/faster-whisper是一个使用 CTranslate2 重新实现的 OpenAI Whisper 模型,旨在提高转录速度和效率。 它显著提高了处理速度,与原始 Whisper 模型相比,保持了相同的准确性的同时,速度提升了最多 4 倍,并且降低了内存使用量。 此外,它支持 CPU 和 GPU 上的 8 位量化,进一步...
升级faster-whisper 至 1.1.0 版本 详见:https://github.com/SYSTRAN/faster-whisper/releases 多语言模式 Large-V3-turbo 模型支持 ... 修复WhisperX 相关bug 修复VAD 阈值选项 UI 相关问题 提示 安装包过大无法上传安装文件,转为使用分割自解压程序形式发布 需要安装 ffmpeg 0.8.1 Changes Upgrade faster...
In order to use GPU acceleration with Faster Whisper, both CUDA 11.2 and cuDNN 8 must be installed. You may want to install it in a virtual environment like Anaconda. Google Colab You can also run this Web UI directly onGoogle Colab, if you haven't got a GPU powerful enough to run ...
# WAVE_OUTPUT_FILENAME = './out/faster_whisper_' + common.get_bj_time(4) + '.wav' frames = audio_listen(config.get("talk", "volume_threshold"), config.get("talk", "silence_threshold")) # 将音频保存为WAV文件 with wave.open(WAVE_OUTPUT_FILENAME, 'wb') as wf: wf.setnchannels(...
CheshireCC/faster-whisper-GUIPublic NotificationsYou must be signed in to change notification settings Fork117 Star1.9k New issue Open danielSHANopened this issueJul 23, 2024· 2 comments Open opened this issueJul 23, 2024· 2 comments
v3ucnwants to merge3commits intoRVC-Boss:mainfromv3ucn:添加-faster-whisper-转写多种语言,提高效率 The head ref may contain hidden characters:"\u6DFB\u52A0-faster-whisper-\u8F6C\u5199\u591A\u79CD\u8BED\u8A00\uFF0C\u63D0\u9AD8\u6548\u7387" ...
能够解决whisper断句混乱的问题,前提是输出的字幕有标点符号,应该什么语言都行。用chatgpt生成三、四句和视频相对应的台词,比如游戏直播,我就以游戏主播的口吻生成几句带标点的话(和视频同语言),然后复制到“初始提示词”中,如果你是0.8.0版本,还需要复制到“热词”中;然后还需要勾选“循环提示。”这样就能解决没...
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-...